METAHEURISTIC OPTIMIZATION OF RESOURCE PLANNING AND BUSINESS PROCESS MANAGEMENT IN RAILWAY TRANSPORT

Abstract

Modern rail transport operates under increasing requirements for capacity, reliability, safety and resource efficiency. The planning of rolling stock, locomotive crews, maintenance activities and infrastructure resources is a complex optimization problem involving multiple constraints and interrelated business processes. Traditional optimization methods often fail to provide solutions within an acceptable timeframe for large-scale problems, which motivates the use of metaheuristic algorithms. This article proposes a conceptual model for optimizing resource planning in rail transport by applying metaheuristic methods. The possibilities of using genetic algorithm, anthill colony optimization, particle swarm optimization, simulated annealing, and taboo search have been explored to optimize schedules, locomotive allocation, crew planning, and maintenance resources. A business process model is proposed, integrating optimization algorithms into operational planning and resource management. The expected results include reduced operating costs, better use of resources, increased reliability of the transport process and improved quality of services, providing a basis for the deployment of intelligent systems to support solutions in rail transport.